Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative

Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative View ORCID Profile Mégane Pizzimenti , View ORCID Profile Ayush Kalia , View ORCID Profile Jamie A. Toghranegar , View ORCID Profile Mohamed Ebraheem , View ORCID Profile Nicholas Cummins , View ORCID Profile Satrajit S. Ghosh , View ORCID Profile James T. Anibal , View ORCID Profile Rhoda Au , View ORCID Profile Arian Azarang , View ORCID Profile Ruth H. Bahr , View ORCID Profile Steven D. Bedrick , View ORCID Profile Hugo Botha , View ORCID Profile Oita C. Coleman , View ORCID Profile Abir Elbeji , View ORCID Profile Lampros C. Kourtis , View ORCID Profile Anaïs Rameau , View ORCID Profile Jaskanwal Deep Singh Sara , View ORCID Profile Stephanie W. Watts , View ORCID Profile Daria Hemmerling , View ORCID Profile Jiri Mekyska , View ORCID Profile Marisha L. Speights , the Bridge2AI Voice Consortium , the eVoiceNet COST Action (CA24128) , View ORCID Profile Jean-Christophe Bélisle-Pipon , View ORCID Profile Yael E. Bensoussan , View ORCID Profile Guy Fagherazzi doi: https://doi.org/10.1101/2025.10.23.25338518 Mégane Pizzimenti 1 Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health , Strassen, Luxembourg PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Mégane Pizzimenti Ayush Kalia 2 USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery, University of South Florida , Tampa, FL, United States 3 Department of Internal Medicine, Yale School of Medicine , New Haven, United States BSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Ayush Kalia Jamie A. Toghranegar 2 USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery, University of South Florida , Tampa, FL, United States SLPD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jamie A. Toghranegar Mohamed Ebraheem 2 USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery, University of South Florida , Tampa, FL, United States MSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Mohamed Ebraheem Nicholas Cummins 4 Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King’s College London , London, United Kingdom PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nicholas Cummins Satrajit S. Ghosh 5 McGovern Institute for Brain Research, Massachusetts Institute of Technology , Cambridge, MA, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Satrajit S. Ghosh James T. Anibal 6 Center for Interventional Oncology, NIH Clinical Center, National Institutes of Health , Bethesda, United States 7 Computational Health Informatics Lab, Institute of Biomedical Engineering, University of Oxford , Oxford, United Kingdom BSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for James T. Anibal Rhoda Au 8 Department of Medicine, Boston University Chobanian & Avedisian School of Medicine , Boston, Massach us etts, United States 9 Department of Anatomy & Neurobiology, Boston University Chobanian & Avedisian School of Medicine , Boston, Massach us etts, United States 10 Boston University Alzheimer’s Disease Research Center , Boston, Massach us etts, United States 11 The Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine , Boston, Massach us etts, United States 12 Department of Epidemiology, Boston University School of Public Health , Boston, Massach us etts, United States 13 Department of Neurology, Boston University Chobanian & Avedisian School of Medicine , Boston, Massach us etts, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Rhoda Au Arian Azarang 14 Department of Radiology, The University of North Carolina at Chapel Hill , Chapel Hill, NC, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Arian Azarang Ruth H. Bahr 15 Department of Communication Sciences & Disorders, University of South Florida , Tampa, FL, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Ruth H. Bahr Steven D. Bedrick 16 Departments of Medical Informatics and Clinical Epidemiology and Medicine, Oregon Health and Science University , Portland, OR, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Steven D. Bedrick Hugo Botha 17 Department of Neurology, Mayo Clinic , Rochester, MN, United States MB, ChB Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Hugo Botha Oita C. Coleman 18 Open Voice TrustMark Initiative , Apex, NC, United States BSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Oita C. Coleman Abir Elbeji 1 Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health , Strassen, Luxembourg PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Abir Elbeji Lampros C. Kourtis 19 Alzheimer’s Drug Discovery Foundation , Boston, MA, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Lampros C. Kourtis Anaïs Rameau 20 Sean Parker Institute for the Voice, Department of Otolaryngology-Head & Neck Surgery, Weill Cornell Medical College , New York, NY, United States MD, MSc Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Anaïs Rameau Jaskanwal Deep Singh Sara 21 Department of Cardiovascular Medicine, Mayo Clinic , Rochester, MN, United States 22 Minneapolis Heart Institute and Minneapolis Heart Institute Foundation, Abbott Northwestern Hospital , Minneapolis, Minnesota, United States MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jaskanwal Deep Singh Sara Stephanie W. Watts 2 USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery, University of South Florida , Tampa, FL, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Stephanie W. Watts Daria Hemmerling 23 Department of Measurement and Electronics, AGH University of Krakow , Kraków, 30-059, Poland PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Daria Hemmerling Jiri Mekyska 24 Department of Telecommunications, Brno University of Technology , Brno, Czech Republic 25 Central European Institute of Technology (CEITEC), Masaryk University , Brno, Czech Republic PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jiri Mekyska Marisha L. Speights 26 Department of Communication Sciences and Disorders, Northwestern University , Evanston, Illinois 60202, United States PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Marisha L. Speights Jean-Christophe Bélisle-Pipon 27 Department of Bio-ethics, Faculty of Health Sciences, Simon Fraser University , Burnaby, British Columbia, Canada PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jean-Christophe Bélisle-Pipon Yael E. Bensoussan 2 USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery, University of South Florida , Tampa, FL, United States MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Yael E. Bensoussan Guy Fagherazzi 1 Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health , Strassen, Luxembourg PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Guy Fagherazzi For correspondence: Guy.Fagherazzi{at}lih.lu Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Importance Voice-based health technologies are growing rapidly, but they lack standardized terminology, which hinders interdisciplinary collaboration, research quality, and clinical translation. Objective The objective of this work is to develop universally accepted definitions in the rapidly evolving field of vocal biomarkers, as part of the VOCAL ( V ocal Biomarker Guidelines for O ntology, C lassification, A pplication, and L ogistics) initiative, a structured, international consensus-based framework that aims to provide standards, and guidelines. Design VOCAL is a rigorous, international, multi-stage consensus-building study conducted in 2024-2025. Setting Multi-institutional collaboration between representatives from the Bridge2AI-Voice Consortium (North America) and the eVoiceNet Network (European Union), culminating in an in-person workshop at the 2025 Bridge2AI Voice Symposium. Participants A group of 24 international experts in medicine, clinical research, speech and language, audio signal processing, statistics, methodology, regulation, ethics. Methods VOCAL’s iterative process involved five rounds of review, feedback, and an in-person workshop at the international 2025 Bridge2AI Voice Symposium, ensuring the incorporation of diverse perspectives and achieving a robust agreement on the proposed definitions. Main outcomes and measures Consensus-based definitions for vocal biomarkers, spanning from broad concepts (biomarker, digital biomarker, vocal biomarker) to domain-specific measures (cardio-respiratory acoustic, voice, speech/articulatory, cognitive/language). Results A hierarchical continuum model of vocal biomarkers was established. We first distinguished between the concepts of vocal measures and vocal biomarkers. We then defined terms from broad, overarching concepts (Level 0: Biomarker, Digital Biomarker, Vocal Biomarker) to more specific physiological and cognitive domains (Level 1: Cardio-Respiratory Acoustic; Level 2: Voice; Level 3: Speech/Articulatory; Level 4: Cognitive/Language, including linguistic and paralinguistic subtypes). Conclusions and Relevance This work provides a shared vocabulary that is essential for fostering communication through interdisciplinary collaboration, improving the quality and efficiency of research and development, and ensuring the ethical, reliable, and scalable deployment of future voice-based health technologies. It lays foundational groundwork for upcoming guidelines and standards, which are crucial for advancing the field of vocal biomarkers into widespread clinical utility. Question Can we establish an international consensus on the definitions related to vocal biomarkers? Findings Through a multi-stage international consensus process involving expert representatives from the Bridge2AI-Voice Consortium and eVoiceNet Network, a hierarchical model of vocal biomarkers was developed, defining terms from broad concepts (biomarker, digital biomarker, vocal biomarker) to specific physiological and cognitive domains (cardio-respiratory acoustic, voice, speech/articulatory, cognitive/language). Meaning Standardized definitions for vocal biomarkers provide an essential shared vocabulary for interdisciplinary collaboration and lay the foundational groundwork for future guidelines needed to advance the implementation of voice-based health technologies into clinical practice and clinical research. Introduction In recent years, the concept of vocal biomarkers has garnered considerable attention for its transformative potential in detecting, monitoring, and managing various health conditions through the analysis of voice-based technologies. 1 , 2 Vocal biomarkers fall under the broader category of digital biomarkers, which are objective and quantifiable health indicators derived from data collected via digital devices such as wearables and sensors. These non-invasive digital biomarkers promise to revolutionize clinical trials and healthcare delivery by enabling continuous, objective, and patient-centered data collection. 3 A key barrier to making vocal biomarkers a reality is the presumption that any digitally acquired voice metric is a vocal biomarker, despite not having undergone rigorous validation. Making a parallel with imaging and blood-based biomarkers, extensive research and investment over many years have gone into validating Alzheimer’s disease imaging and blood-based measures as biomarkers. This same careful, scientific approach for biomarker validation is not currently being applied to digital data. When validating any biomarker, the context of use must be defined to establish it as a biomarker for a specific disease. Thus, moving the field from measuring features of the voice and speech to validated vocal biomarkers will require the time, energy, and investment necessary to undergo validation processes that biological biomarkers have already undergone. The path to validated biomarkers is generally defined by authorities such as the Food and Drug Administration (FDA) or the European Medicines Agency (EMA). Guidelines for digital biomarkers from these regulatory agencies are still in their nascent stages. Thus, there is an opportunity to collaborate with them in developing validation pipelines for various types of vocal biomarkers. We provide definitions of different types of vocal biomarkers below, with the caveat that validation is needed for each subtype within each category and for a specific context of use. Future work will require a transparent validation process and address concerns regarding artificial intelligence (AI)-driven approaches to vocal biomarker identification, details of which are discussed below. Once validated, vocal biomarkers will be unique among digital biomarkers in that they derive from the interplay of multiple physiological systems (respiratory, phonatory, articulatory, and cognitive) captured through audio. Their integration into healthcare reflects a broader movement toward more real-time and remote health sensing. 4 , 5 In Parkinson’s disease, speech and language impairments are common and often precede motor dysfunction; features such as reduced loudness, monotone speech, imprecise articulation, and altered rhythm show strong potential for early detection and tracking disease severity and progression. 6 In Alzheimer’s disease, lexical-semantic and acoustic measures show high diagnostic performance for mild cognitive impairment, correlate with amyloid-β status and hippocampal volume, and predict 2-year disease progression, supporting their use for early detection and monitoring. 7 Psychiatric and neurodevelopmental conditions likewise exhibit distinctive vocal patterns: for example, depressed individuals tend to speak more slowly, quietly, and with flattened prosody (with frequent pauses), and these acoustic characteristics correlate with depression severity. 8 In chronic heart failure, voice analysis offers a promising, cost-effective, and convenient alternative for diagnosing, risk prediction, and telemonitoring clinical outcomes. 9 Vocal biomarkers also help identify smoking status from ecological audio recordings, 10 and show promise as a screening or monitoring tool for conditions like type 2 diabetes. 11 Despite this rapid growth, a fundamental challenge persists: the absence of universally accepted definitions for key terms such as “voice biomarkers”, “vocal biomarkers”, and “speech biomarkers”, among others. These terms are frequently used interchangeably in the literature, 10 , 12 – 18 , yet they reflect features originating from distinct physiological and cognitive systems. A review of existing research reveals a wide variance in definitions, often leading to nearly as many interpretations as there are articles on the topic. 4 Such terminological ambiguity presents a significant barrier to scientific progress. 19 It hampers collaboration across diverse disciplines, complicates efforts to share data, and impedes the development of standardized methodologies and best practices. 20 Without a common language, the field risks fragmentation and inefficiency, ultimately undermining its scientific advancement, regulatory assessment, clinical translation, and trustworthiness of its innovation. 21 , 22 This challenge is further reinforced by a set of interrelated risks that threaten the field’s coherence and scalability. The widespread use of AI, proprietary algorithms, and closed datasets has created a “black box” problem, where the lack of transparency limits reproducibility and erodes trust among researchers, clinicians, and regulators. In parallel, inconsistent terminologies and disciplinary silos exacerbate confusion, highlighting the urgent need for a shared, evolving vocabulary. The technical landscape adds further complexity, as voice data is often massive, heterogeneous, and collected under diverse conditions, making integration across studies difficult without adherence to FAIR (Findable, Accessible, Interoperable, Reusable) principles. 23 Voice data-specific regulatory frameworks remain fragmented and difficult to navigate, particularly across regions, posing significant hurdles to clinical validation and implementation. 24 Additionally, concerns about privacy, data ownership, and ethical use of sensitive voice data persist, 25 alongside practical challenges such as ensuring sustained patient engagement in digital trials. 26 A recent survey of stakeholders in voice AI development emphasized the need for ethically sourced, diverse, and transparent data practices, calling for trustworthiness not just as a technical feature but as a guiding norm. 25 The lack of consensus also impairs the development of methodological infrastructure. While master protocols are now standard in clinical trials and other biomarker fields, vocal biomarker research lacks unified frameworks, resulting in heterogeneous data collection, feature extraction, and analysis methods. 4 This absence complicates validation and clinical scalability. These converging barriers underscore the pressing need for community-driven standards, transparent methodologies, and harmonized regulatory pathways to unlock the full potential of vocal biomarkers. Establishing a unified framework for vocal biomarkers is therefore essential. Standardization will provide a shared vocabulary that facilitates interdisciplinary collaboration, supports data interoperability, and enables reproducibility of research findings. This foundation is critical for advancing vocal biomarker research from exploratory studies to reliable clinical applications. To address this challenge, this paper proposes a set of foundational definitions as the first step of the VOCAL initiative (standing for V ocal Biomarker Guidelines for O ntology, C lassification, A pplication, and L ogistics), a structured, international framework for harmonizing practices and guiding the field of vocal biomarkers. We aim to develop a shared and controlled vocabulary that promotes clarity and consistency across disciplines. This will facilitate effective communication among all stakeholders and the general public, and it will guide the development of best practices for the field. Methods Consensus-Building Process To develop clear and widely applicable definitions of vocal biomarkers, a structured, multi-stage consensus-building process was employed. This approach was meticulously designed to incorporate diverse perspectives from interdisciplinary stakeholders, ensuring transparency and rigor throughout the development of the framework. The iterative nature of the process enabled continuous refinement and validation of the proposed definitions, resulting in a robust and widely accepted outcome. Participants The consensus process involved three distinct groups of participants, ensuring broad representation and a comprehensive range of expertise: ● Internal Team (n = 7): This group comprised core members directly involved in the initial drafting of definitions and the coordination of the entire consensus process. They were leaders (YB, GF) and representatives of two large international consortia on vocal biomarkers: the Bridge2AI Voice Consortium and the eVoiceNet network. Their expertise spanned critical areas, including laryngology, speech-language pathology, digital epidemiology, AI, research methodology, and bioethics. This diverse composition ensured a strong foundational understanding of both clinical and technical aspects of vocal biomarkers. ● Selected Group of Experts (n = 5): This group consisted of international academic researchers with highly specialized expertise in speech analysis, clinical research, and the development and commercialization of vocal biomarkers. Their focused input provided in-depth technical and methodological critique, refining the precision and scientific accuracy of the definitions. ● Broader Expert Group (n = 18): This extended panel comprised a diverse array of researchers, clinicians, voice AI researchers, and stakeholders from a wide range of relevant disciplines (Clinical and Medical Sciences, Speech and Language Sciences, Engineering and Technical Fields, Statistics and Methodology, Regulation, Ethics, and Translation). This group provided a comprehensive review and validation of the definitions from various practical and theoretical standpoints, ensuring their applicability across the broader scientific and clinical landscape. Iterative Process The process was organized into five iterative rounds of review and feedback, systematically designed to progressively refine the definitions and achieve strong consensus among all participants (see Figure 1 ; Supp Table 1 ). ● Initial Draft and First Round of Review: The internal team initiated the process by drafting preliminary definitions of vocal biomarkers. A comprehensive review informed this of existing literature and terminology. Following this, team members individually reviewed and provided comments on the draft. A subsequent group meeting was held to discuss and consolidate all feedback, leading to the first set of revisions (Revision #1). ● Second Round of Review: The revised definitions (Revision #1) were then shared with both the internal team and the selected group of experts. Participants provided written feedback, which was then discussed in an online workshop. This workshop focused on identifying points of agreement and divergence, and the collective input led to a second set of revisions (Revision #2). ● Third Round of Review: The updated definitions (Revision #2) were again reviewed by the internal team and the selected experts. A second online workshop was convened to refine terminology further and address any remaining ambiguities or concerns. This meticulous discussion resulted in a third revision (Revision #3), which brought the definitions closer to a final consensus. ● Fourth Round of Review: The extensively revised definitions (Revision #3) were presented to the broader expert group for review and finalization. An in-person workshop was conducted at the Voice AI Conference in Tampa, April 2025, during which participants formally voted by a show of hands on their agreement or disagreement with each presented definition. Any definition receiving disagreement from 25% or more of the participants was subjected to further discussion and revision. This iterative refinement continued until a consensus was achieved for all definitions. ● Fifth Round of Review and Finalization : Feedback from the workshop was further integrated into a final set of definitions developed by the internal team. Following this final round, all co-authors reviewed and approved the definitions and the overarching framework presented in this paper. Download figure Open in new tab Figure 1. Flowchart of the iterative process to establish the definitions of key terms of the VOCAL initiative The process included an initial internal team draft and first review, two rounds of review with selected experts, a consensus workshop with a broader expert group, and a final review and approval. The number of participants at each stage is indicated (n). View this table: View inline View popup Table 1. Level 0 Definitions This rigorous process ensured that all concerns were thoroughly addressed through collective discussion before the definitions were finalized. Results To capture the layered complexity of vocal biomarkers while maintaining clarity and usability, the definitions were structured across different levels of granularity, forming a continuum model. This hierarchical approach enables both a broad conceptual understanding and precise categorization based on the underlying physiological and cognitive systems involved in voice production. ● Level 0 represents broad, overarching terms in the biomarker domain. These foundational definitions are intended to frame the scope of discussion and provide shared reference points across diverse disciplines and technologies. ● Levels 1 to 4 provide more specific and structured definitions of terms that fall under the umbrella of vocal biomarkers. These are categorized based on the stage or domain of vocal production and analysis, ranging from the earliest physiological processes to higher-level cognitive functions (see Figure 2 and Figure 3 ). Download figure Open in new tab Figure 2. Hierarchical continuum of vocal biomarkers: from voice production to high-level cognition The pyramid illustrates the hierarchy of vocal biomarkers, organized by physiological drivers and complexity. Level 1 biomarkers (blue) represent cardio-respiratory acoustic biomarkers driven by respiration and aerodynamics. Level 2 biomarkers (green) reflect voice biomarkers arising from phonation. Level 3 biomarkers (yellow) capture speech and articulatory biomarkers shaped by articulation and resonance. Level 4 biomarkers (orange) represent cognitive and language biomarkers arising from high-order neurological processes. Complexity increases from the base to the apex of the pyramid. Corresponding anatomical regions associated with each biomarker type are shown on the left. Created in https://BioRender.com Download figure Open in new tab Figure 3. Vocal Biomarkers Levels 0-4 Vocal biomarkers can be categorized across four levels based on their physiological and cognitive origins. Level 0: Biomarker, Digital Biomarker, Vocal biomarker represent broad, overarching terms. Level 1: Cardio-Respiratory Acoustic Biomarkers (CRA) relate to acoustic signals associated with respiration and cardiac function (e.g., breathing sounds, cough acoustics). Level 2: Voice Biomarkers pertain to features of phonation and vocal fold vibration (e.g., harmonic-to-noise ratio, cepstral peak prominence, fundamental frequency). Level 3: Speech/Articulatory Biomarkers involve articulatory processes and speech motor control (e.g., articulation rate, speech rate, articulatory precision, speech prosody and rhythm). Level 4: Cognitive/Language Biomarkers reflect the content of speech, including lexical access, word pairing, syntax, and paralinguistic elements such as emotion, cultural cues, and dialects (e.g., vocabulary, syntax). Created in https://BioRender.com It is crucial to understand that these categories are not mutually exclusive and often overlap, reflecting the interconnected nature of human voice production. Furthermore, extracted features can be interpreted as different types of biomarkers, depending on the specific context in which they are applied. Level 0 Definitions Table 1 establishes the foundational terminology for the entire framework, ensuring that readers from diverse backgrounds, including clinicians, engineers, researchers, and regulators, have a common understanding of “Biomarker,” “Digital Biomarker,” and “Vocal Biomarker” before delving into more specific categories (see Supp Figure S1). This clarity is paramount for interdisciplinary discourse and regulatory alignment. Level 1-4 Definitions Table 2 breaks down the complex domain of vocal biomarkers into actionable, physiologically grounded categories. By providing clear definitions, examples, and illustrations, it serves as a practical guide for researchers and clinicians to accurately classify and interpret vocal features, thereby reducing ambiguity and facilitating standardized research design and reporting. View this table: View inline View popup Table 2. Level 1-4 Definitions Discussion This study presents the first stage of the VOCAL (Vocal Biomarker Guidelines for Ontology, Classification, Application, and Logistics) initiative, offering foundational definitions that aim to address longstanding terminological fragmentation in the field of vocal biomarkers. By introducing a layered, physiologically grounded vocabulary organized across five hierarchical levels, the framework establishes a shared reference system that facilitates interdisciplinary collaboration, supports regulatory alignment, and promotes scientific rigor. In doing so, it fills a critical gap in the biomedical and digital health landscape, where vocal biomarkers are increasingly positioned as scalable, non-invasive tools for the early detection and monitoring of diverse health conditions. Rethinking Voice Data and Analytics Through a Unified Lexicon This study’s most consequential contribution is the reframing of “vocal biomarkers” not as a monolithic or interchangeable term, but as a continuum of overlapping physiological and cognitive signals. The framework intentionally avoids drawing rigid boundaries, opting instead for a layered structure that mirrors the interconnected nature of voice production, encompassing breath and muscle control, as well as language, memory, and emotion. This continuum model provides researchers and clinicians with a shared yet flexible vocabulary that can accommodate both scientific precision and real-world variability. What makes this framework novel is its capacity to capture complexity without collapsing it. The five-level structure, from Level 0’s foundational definitions (biomarker, digital biomarker, vocal biomarker) to Level 4’s cognitive and language biomarkers, helps differentiate vocal signals not only by signal type, but also by the physiological or cognitive systems they reflect. For instance, Level 1 (cardio-respiratory acoustic biomarkers) isolates signals, such as breath pauses or cough acoustics, which are distinct from Level 2’s voice-source features, including pitch and harmonicity. Level 3 focuses on articulatory dynamics (tongue, lip, and jaw coordination), while Level 4 examines how language and social cognition are conveyed through lexical and paralinguistic cues. Importantly, this stratification does not imply mutually exclusive categories. The framework recognizes that many vocal features traverse multiple domains. Pitch, for example, may simultaneously carry phonatory, prosodic, and emotional information depending on the context. By allowing such overlaps, the model resists the oversimplification that often characterizes both academic studies and commercial applications in the voice-AI space. This layered approach also acts as a conceptual correction to the field’s current fragmentation. Too often, research on “vocal biomarkers” has used the term without clarifying what part of the vocal system is being measured, or for what purpose. This imprecision limits interoperability between datasets, obscures reproducibility, and undermines both clinical translation and regulatory review. The proposed definitions address this gap by creating clear referents across disciplines while still allowing interpretive flexibility. Beyond classification, the framework has normative and regulatory implications. By standardizing language across a fast-evolving and commercially saturated space, it challenges the opacity of proprietary systems that often treat voice as an undifferentiated input stream. A common lexicon, co-produced by experts across laryngology, AI, neuroscience, ethics, and clinical research, fosters transparency and makes space for critical scrutiny of what is being measured, how, and why. In this way, the framework functions not only as a taxonomic scaffold but as an epistemic and ethical intervention. It realigns the field around grounded, interpretable, and shared understandings of voice and its relationship to health, an essential foundation as vocal biomarkers move from exploratory research toward clinical integration. Limitations While this framework represents a significant step toward definitional coherence in vocal biomarker research, several limitations must be acknowledged. First, the process, although interdisciplinary and international, remains in its early stages. It centered primarily on researchers and professionals already embedded in consortia or academic networks. The voices of patients, regulators, and public health decision-makers from underrepresented regions were missing. Their perspectives are essential, particularly when voice data intersects with issues of trust, access, and cultural specificity. Second, the framework is intentionally definitional; it does not yet establish guidance on study design, feature extraction protocols, or validation metrics. While the definitions offer much-needed clarity on what is being measured, they do not resolve how those measurements should be standardized, interpreted, or integrated into clinical workflows. Questions regarding longitudinal stability, generalizability across languages and populations, and device dependence of vocal features remain outside the scope of this initial effort. Third, the flexible continuum approach (while a strength conceptually) may present practical challenges in operationalization. Some features can be categorized at more than one level, depending on their context. This ambiguity is intentional and reflects the non-discrete nature of vocal production, but it may complicate automated classification, regulatory labeling, or systematic reviews that require sharper boundaries. Finally, while the consensus process was rigorous and iterative, it does not constitute empirical validation. Whether these definitions improve reproducibility, regulatory acceptance, or interdisciplinary collaboration remains to be seen. The framework should thus be seen as provisional and living: a starting point for dialogue, not a final verdict. Contribution to Vocal Biomarkers Development and Clinical Uptake The definitional framework proposed in this paper addresses a longstanding barrier in the field of vocal biomarkers: the lack of precise and consistent terminology. By structuring vocal biomarkers along a physiologically grounded continuum, the framework offers a common language for describing and interpreting voice-based health data. This contribution extends beyond academic precision, laying the groundwork for broader adoption, accountability, and clinical relevance. Standardization acts as a catalyst for trust and uptake across the healthcare ecosystem. When definitions are unambiguous and widely accepted, clinicians are better equipped to interpret findings, patients are more likely to trust voice-based technologies, and regulators can more efficiently evaluate and approve them. This creates a reinforcing cycle: clarity builds trust, trust encourages adoption, and adoption drives further research, innovation, and investment. The framework also addresses a significant challenge in digital health: the opacity of proprietary systems. Open, transparent definitions reduce the “black box” problem by making it easier to understand what is being measured, how it is measured, and why. This fosters reproducibility, supports ethical governance, and enables cross-study comparisons, thereby reducing duplication and accelerating progress. For patients and clinicians alike, shared terminology enhances communication and facilitates the meaningful use of healthcare information. For third-party payers (e.g., private and public insurers) and regulators, standardization reduces uncertainty and facilitates alignment with existing biomarker approval pathways. In all cases, the framework advances the conditions necessary for responsible innovation and sustainable integration of vocal biomarkers into healthcare systems. Future Research This framework offers a foundation, not an endpoint. Future research should test the practical utility of the continuum model across various use cases, examining whether it improves consistency in feature labeling, interpretability, and reproducibility in both research and clinical settings. Applying the definitions in comparative studies may clarify their impact on model transparency and cross-study compatibility. Methodological extensions are also needed, which include reporting standards aligned with the Levels, protocols for labeling multi-level features, and guidance on handling ambiguous cases. Embedding the framework into shared methodological infrastructures (such as master protocols) would support broader uptake and interoperability. Cultural, linguistic, and ethical dimensions must also be taken into account. Vocal features are shaped by more than physiology; they carry social and contextual meaning. Research must examine how definitions perform across diverse populations and communication norms, and avoid encoding bias into measurement or interpretation. Participatory approaches will be crucial in ensuring that voice-based tools are designed and deployed fairly and equitably. Finally, alignment with regulatory standards is essential. Mapping the framework to existing evidentiary categories (such as digital endpoints or AI-based diagnostics) can help establish vocal biomarkers as clinically valid and ethically deployable tools, not speculative proxies. As the field matures, this definitional groundwork should evolve alongside it, anchoring technical progress in clarity, accountability, and shared understanding. Conclusion This paper presents the first structured, consensus-based definitional framework for vocal biomarkers, responding to a critical need for clarity, consistency, and interoperability in a rapidly evolving field. Developed through a rigorous, multi-stage process involving international experts across disciplines, the framework offers a shared vocabulary that reflects the physiological and cognitive dimensions of voice production. By anchoring vocal biomarkers in a layered, interpretable structure, this work provides a foundation for interdisciplinary collaboration, ethical development, and clinical translation. It helps unify fragmented research efforts, supports reproducibility, and facilitates regulatory alignment, paving the way for future guidelines, validation standards, and implementation practices. As voice continues to emerge as a rich source of health-relevant data, a common language is indispensable. This framework offers more than definitional clarity; it offers a path toward trustworthy, patient-centered, and clinically impactful voice-based health technologies. Data Availability All data produced in the present work are contained in the manuscript Acknowledgments We thank Claire Bortolotto for her contributions during selected meetings of the first round of review. This article/publication is based upon work from COST Action eVoiceNet (CA24128) supported by COST (European Cooperation in Science and Technology). Footnotes the Bridge2AI Voice Consortium : Yael E. Bensoussan: University of South Florida, Tampa, FL, USA. Olivier Elemento: Weill Cornell Medicine, New York, NY, USA. Jean Christophe Bélisle-Pipon: Simon Fraser University, Burnaby, BC, Canada. David Dorr: Oregon Health & Science University, Portland, OR, USA. Satrajit Ghosh: Massachusetts Institute of Technology, Boston, MA, USA. Alistair Johnson: Microsoft, Toronto, ON, Canada. Phillip Payne: Washington University in St. Louis, St. Louis, MO, USA. Maria E. Powell: Vanderbilt University Medical Center, Nashville, TN, USA. Anaïs Rameau: Weill Cornell Medicine, New York, NY, USA. Vardit Ravitsky: The Hastings Center, Garrison, NY, USA. Alexandros Sigaras: Weill Cornell Medicine, New York, NY, USA. Jordan Lerner-Ellis: University of Toronto Mount Sinai Hospital: Sinai Health, Toronto, ON, Canada. Shaheen Awan: University of Central Florida, Orlando, FL, USA. Ruth Bahr: University of South Florida, Tampa, FL, USA. Frank Rudzicz: Dalhousie University, Toronto, ON, Canada. Jennifer Siu: Hospital for Sick Children, Toronto, ON, Canada. Stephanie Watts: University of South Florida, Tampa, FL, USA. Yassmeen Abdel-Aty: University of South Florida, Tampa, FL, USA. Steven Bedrick: Oregon Health & Science University, Portland, OR, USA. Alexander Bernier: McGill University, Montreal, Quebec, Canada. Micah Boyer: University of South Florida, Tampa, FL, USA. Moroni Berrios: University of South Florida, Tampa, FL, USA. John Brown: University of South Florida, Tampa, FL, USA. Kenneth Fletcher: Vanderbilt University Medical Center, Nashville, TN, USA. Hortense Gallois: Simon Fraser University, Burnaby, BC, Canada. C. Gaelyn Garrett: Vanderbilt University Medical Center, Nashville, TN, USA. Alexander Gelbard: Vanderbilt University Medical Center, Nashville, TN, USA. Amer Ghavanini: Trillium Health Partners and University of Toronto, Toronto, Ontario, Canada. Karim Hanna: University of South Florida, Tampa, FL, USA. William Hersh: Oregon Health & Science University, Portland, OR, USA. Jennifer Jain: University of South Florida, Tampa, FL, USA. Brena Juan Guardela: University of South Florida, Tampa, FL, USA. Kenji Kobayashi: Vanderbilt University Medical Center, Nashville, TN, USA. Andrea Krussel: Washington University in St. Louis, St. Louis, MO, USA. Sarah Rohde: Vanderbilt University Medical Center, Nashville, TN, USA. Jillian Rossi: University of South Florida, Tampa, FL, USA. Laurie Russell: SickKids, Toronto, ON, Canada. Samantha Salvi Cruz: Vanderbilt University Medical Center, Nashville, TN, USA. Shrramana Ganesh Sudhakar: University of South Florida, Tampa, FL, USA. Megan Urbano: University of South Florida, Tampa, FL, USA. Kimberly Vinson: Vanderbilt University Medical Center, Nashville, TN, USA. Theresa Zesiewicz: University of South Florida, Tampa, FL, USA. Jamie Toghranegar: University of South Florida, Tampa, FL, USA. Cynthia Kostelnik: University of South Florida, Tampa, FL, USA. James Anibal: University of Oxford; National Institutes of Health, Oxford, UK; Bethesda, Maryland, USA. Kirollos Armosh: University of South Florida, Tampa, FL, USA. Helena Beltran: University of South Florida, Tampa, FL, USA. Isaac Bevers: Massachusetts Institute of Technology, Cambridge, MA, USA. Rahul Brito: Massachusetts Institute of Technology, Cambridge, MA, USA. Mahmoud Elmahdy: University of South Florida, Tampa, FL, USA. Evan Ng: SickKids, Toronto, ON, Canada. Kaley Jenney: Massachusetts Institute of Technology, Cambridge, MA, USA. Megha Kalia: University of South Florida, Tampa, FL, USA. Alisa Krause: University of South Florida, Tampa, FL, USA. Genelle Leo: University of South Florida, Tampa, FL, USA. Chloe Loewith: Simon Fraser University, Burnaby, BC, Canada. Siyu Miao: SickKids, Toronto, ON, Canada. Tempestt Neal: University of South Florida, Tampa, FL, USA. Claire Premi-Bortolotto: Simon Fraser University, Burnaby, BC, Canada. John Ramos: Weill Cornell Medicine, New York, NY, USA. John Stark: University of South Florida, Tampa, FL, USA. Venkata Swarna Mukhi: Oregon Health & Science University, Portland, OR, USA. Julie Tu: Mount Sinai Hospital, Toronto, ON, Canada. Claire Wilson: Simon Fraser University, Burnaby, BC, Canada. Madeleine Zanin: Sinai Health, Toronto, ON, Canada. Mohamed Ebraheem: University of South Florida, Tampa, FL, USA. Emily Evangelista: University of South Florida, Tampa, FL, USA. Anna Goldenberg: SickKids, Toronto, ON, Canada. Ayush Kalia: University of South Florida, Tampa, FL, USA. Vrishni Maharaj: University of South Florida, Tampa, FL, USA. Ana Sophia Avila Martinez: University of South Florida, Tampa, FL, USA. Elijah Moothedan: Florida Atlantic University, Boca Raton, FL, USA. JM Rahman: University of South Florida, Tampa, FL, USA. Jordan Wilke: Massachusetts Institute of Technology, Cambridge, MA, USA the eVoiceNet network : Guy Fagherazzi: Luxembourg Institute of Health, Luxembourg. Ervin Dyrmishi: University of Medicine, Albania. Philipp Aichinger: Medical University of Vienna, Austria. Els Kindt: Katholieke Universiteit Leuven, Belgium. Jovan Galić: University of Banja Luka, Bosnia and Herzegovina. Anna Andreeva: South-West University “Neofit Rilski”, Bulgaria. Anamaria Malešević: Catholic University of Croatia, Croatia. Anto Čartolovni: Catholic University of Croatia, Croatia. Eleni Theodorou: Cyprus University of Technology, Cyprus. Jiri Mekyska: Brno University of Technology, Czech Republic. Sneha Das: Technical University of Denmark, Denmark. Sedat Akleylek: University of Tartu, Estonia. Paavo Alku: Aalto University, Finland. Fabian Kerwagen: University Hospital Würzburg, Germany. Paula Andrea Pérez-Toro: Friedrich-alexander-universitaet Erlangen-nuernberg, Germany. Maria Stamelou: Diagnostikon Kai Therapeftikon Kentron Athinon Ygeia Anonymos Etaireia, Greece. Elina Tripoliti: University College London, United Kingdom. Dávid Sztahó: Budapest University of Technology and Economics, Hungary. Klára Vicsi: Budapest University of Technology and Economics, Hungary. Gaddi Blumrosen: Holon Institute Of Technology, Israel. Yosi Keller: Bar Ilan University, Israel. Anna Esposito: Università della Campania Luigi Vanvitelli, Italy. Grazina Korvel: Vilnius University, Lithuania. Virgilijus Uloza: Lithuanian University Of Health Sciences, Lithuania. Vladimir Despotovic: Luxembourg Institute Of Health, Luxembourg. Elvir Zvrko: Klinicki Centar Crne Gore Podgorica, Montenegro. Catherine Jasserand: Rijksuniversiteit Groningen, Netherlands. Sami Simons: Universiteit Maastricht, Netherlands. Branislav Gerazov: Ss. Cyril and Methodius University in Skopje, North Macedonia. Daria Hemmerling: AGH University of Krakow, Poland. Tomasz Jadczyk: Slaski Uniwersytet Medyczny W Katowicach, Poland. Alberto Abad: Instituto de Engenharia de Sistemas e Computadores – Investigação e Desenvolvimento, Portugal. Isabel Trancoso: Instituto de Engenharia de Sistemas e Computadores – Investigação e Desenvolvimento, Portugal. Dejan Ciric: University Of Nis, Serbia. Peter Pocta: University of Žilina, Slovakia. Jerneja Zganec Gros: Alpineon razvoj in raziskave, d.o.o., Slovenia. Andrej Žgank: Univerza V Mariboru, Slovenia. Marcos Faundez-Zanuy: Fundació TecnoCampus Mataró-Maresme, Spain. Juan Ignacio Godino Llorente: Universidad Politécnica de Madrid, Spain. Katarzyna Hess: Kapharos, Sweden. Ina Kodrasi: Fondation De L’institut De Recherche Idiap, Switzerland. Mathew Magimai Doss: Fondation De L’institut De Recherche Idiap, Switzerland. Selda Ozdemir: Hacettepe University Education, Türkiye. Güzin Ulutaş: Karadeniz Teknik Universitesi, Türkiye. Nicholas Cummins: King’s College London, United Kingdom. Jennifer Williams: University of Southampton, United Kingdom Author affiliations updated: 1) Corrected a misspelling of an author's last name (Cummings → Cummins) 2) Added the Bridge2AI Voice Consortium affiliation 3) Added the eVoiceNet COST Action (CA24128) affiliation References 1. ↵ Fagherazzi G , Fischer A , Ismael M , Despotovic V . Voice for Health: The Use of Vocal Biomarkers from Research to Clinical Practice . Digit Biomark . 2021 ; 5 ( 1 ): 78 – 88 . doi: 10.1159/000515346 OpenUrl CrossRef PubMed 2. ↵ Bensoussan Y , Elemento O , Rameau A . Voice as an AI Biomarker of Health—Introducing Audiomics . JAMA Otolaryngol Neck Surg . 2024 ; 150 ( 4 ): 283 – 284 . doi: 10.1001/jamaoto.2023.4807 OpenUrl CrossRef 3. ↵ Fagherazzi G , Bensoussan Y . The Imperative of Voice Data Collection in Clinical Trials . Digit Biomark . 2024 ; 8 ( 1 ): 207 – 209 . doi: 10.1159/000541456 OpenUrl CrossRef PubMed 4. ↵ Kalia A , Boyer M , Fagherazzi G , Bélisle-Pipon JC , Bensoussan Y . Master protocols in vocal biomarker development to reduce variability and advance clinical precision: a narrative review . Front Digit Health . 2025 ; 7 : 1619183 . doi: 10.3389/fdgth.2025.1619183 OpenUrl CrossRef PubMed 5. ↵ Patel R , Price N , Bahr R , et al. Summary of Keynote Speeches from the 2024 Voice AI Symposium, presented by the Bridge2AI-Voice Consortium . Front Digit Health . 2024 ; 6 . doi: 10.3389/fdgth.2024.1484503 OpenUrl CrossRef 6. ↵ Hajjar I , Okafor M , Choi JD , et al. Development of digital voice biomarkers and associations with cognition, cerebrospinal biomarkers, and neural representation in early Alzheimer’s disease . Alzheimers Dement Amst Neth . 2023 ; 15 ( 1 ): e12393 . doi: 10.1002/dad2.12393 OpenUrl CrossRef 7. ↵ Bauser M , Kraus F , Koehler F , et al. Voice Assessment and Vocal Biomarkers in Heart Failure: A Systematic Review . Circ Heart Fail. Published online April 24 , 2025 : e012303 . doi: 10.1161/CIRCHEARTFAILURE.124.012303 OpenUrl CrossRef 8. ↵ Ayadi H , Elbéji A , Despotovic V , Fagherazzi G . Digital Vocal Biomarker of Smoking Status Using Ecological Audio Recordings: Results from the Colive Voice Study . Digit Biomark . 2024 ; 8 ( 1 ): 159 – 170 . doi: 10.1159/000540327 OpenUrl CrossRef PubMed 9. ↵ Elbeji A , Aguayo G , Fischer A , Fagherazzi G . Identification of vocal biomarkers for screening diabetes and monitoring health of people with diabetes: preliminary results from the COLIVE voice study . Diabetes Technol Ther . 2022 ; 24 ( Suppl.1 ): A224 – A224 . doi: 10.1089/dia.2022.2525.abstracts OpenUrl CrossRef 10. ↵ Kiyoshige E , Ogata S , Kwon N , et al. Developing and testing AI-based voice biomarker models to detect cognitive impairment among community dwelling adults: a cross-sectional study in Japan . Lancet Reg Health West Pac . 2025 ; 59 : 101598 . doi: 10.1016/j.lanwpc.2025.101598 OpenUrl CrossRef PubMed 11. ↵ Mazur A , Costantino H , Tom P , Wilson MP , Thompson RG . Evaluation of an AI-Based Voice Biomarker Tool to Detect Signals Consistent With Moderate to Severe Depression . Ann Fam Med . 2025 ; 23 ( 1 ): 60 – 65 . doi: 10.1370/afm.240091 OpenUrl Abstract / FREE Full Text 12. ↵ Watase T , Omiya Y , Tokuno S . Severity Classification Using Dynamic Time Warping-Based Voice Biomarkers for Patients With COVID-19: Feasibility Cross-Sectional Study . JMIR Biomed Eng . 2023 ; 8 : e50924 . doi: 10.2196/50924 OpenUrl CrossRef 13. Kerwagen F , Bauser M , Baur M , et al. Vocal biomarkers in heart failure-design, rationale and baseline characteristics of the AHF-Voice study . Front Digit Health . 2025 ; 7 : 1548600 . doi: 10.3389/fdgth.2025.1548600 OpenUrl CrossRef PubMed 14. Lin YC , Yan HT , Lin CH , Chang HH . Identifying and Estimating Frailty Phenotypes by Vocal Biomarkers: Cross-Sectional Study . J Med Internet Res . 2024 ; 26 : e58466 . doi: 10.2196/58466 OpenUrl CrossRef PubMed 15. Roland V , Huet K , Harmegnies B , Piccaluga M , Verhaegen C , Delvaux V . Vowel production: a potential speech biomarker for early detection of dysarthria in Parkinson’s disease . Front Psychol . 2023 ; 14 : 1129830 . doi: 10.3389/fpsyg.2023.1129830 OpenUrl CrossRef PubMed 16. Gaur S , Kalani P , Mohan M . Harmonic-to-noise ratio as speech biomarker for fatigue: K-nearest neighbour machine learning algorithm . Med J Armed Forces India . 2024 ; 80 ( Suppl 1 ): S120 – S126 . doi: 10.1016/j.mjafi.2022.12.001 OpenUrl CrossRef 17. Sterner B . Explaining ambiguity in scientific language . Synthese . 2022 ; 200 ( 5 ): 354 . doi: 10.1007/s11229-022-03792-x OpenUrl CrossRef 18. ↵ Livieri G , Mangina E , Protopapadakis ED , Panayiotou AG . The gaps and challenges in digital health technology use as perceived by patients: a scoping review and narrative meta-synthesis . Front Digit Health . 2025 ; 7 . doi: 10.3389/fdgth.2025.1474956 OpenUrl CrossRef 19. ↵ Key Factors Behind IT Implementation Failures in Mid-Sized Healthcare Settings – CapMinds . May 5, 2025 . https://www.capminds.com/blog/key-factors-behind-it-implementation-failures-in-mid-sized-healthcare-settings/ 20. ↵ Babrak LM , Menetski J , Rebhan M , et al. Traditional and Digital Biomarkers: Two Worlds Apart? Digit Biomark . 2019 ; 3 ( 2 ): 92 – 102 . doi: 10.1159/000502000 OpenUrl CrossRef PubMed 21. ↵ Schmidt J , Schutte NM , Buttigieg S , et al. Mapping the regulatory landscape for artificial intelligence in health within the European Union . Npj Digit Med . 2024 ; 7 ( 1 ): 229 . doi: 10.1038/s41746-024-01221-6 OpenUrl CrossRef PubMed 22. ↵ Bélisle-Pipon JC , Powell M , English R , et al. Stakeholder perspectives on ethical and trustworthy voice AI in health care . Digit Health . 2024 ; 10 : 20552076241260407 . doi: 10.1177/20552076241260407 OpenUrl CrossRef PubMed 23. ↵ Tan RKJ , Wu D , Day S , et al. Digital approaches to enhancing community engagement in clinical trials . NPJ Digit Med . 2022 ; 5 ( 1 ): 37 . doi: 10.1038/s41746-022-00581-1 OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted December 03, 2025. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative Mégane Pizzimenti , Ayush Kalia , Jamie A. Toghranegar , Mohamed Ebraheem , Nicholas Cummins , Satrajit S. Ghosh , James T. Anibal , Rhoda Au , Arian Azarang , Ruth H. Bahr , Steven D. Bedrick , Hugo Botha , Oita C. Coleman , Abir Elbeji , Lampros C. Kourtis , Anaïs Rameau , Jaskanwal Deep Singh Sara , Stephanie W. Watts , Daria Hemmerling , Jiri Mekyska , Marisha L. Speights , the Bridge2AI Voice Consortium , the eVoiceNet COST Action (CA24128) , Jean-Christophe Bélisle-Pipon , Yael E. Bensoussan , Guy Fagherazzi medRxiv 2025.10.23.25338518; doi: https://doi.org/10.1101/2025.10.23.25338518 Share This Article: Copy Citation Tools Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative Mégane Pizzimenti , Ayush Kalia , Jamie A. Toghranegar , Mohamed Ebraheem , Nicholas Cummins , Satrajit S. Ghosh , James T. Anibal , Rhoda Au , Arian Azarang , Ruth H. Bahr , Steven D. Bedrick , Hugo Botha , Oita C. Coleman , Abir Elbeji , Lampros C. Kourtis , Anaïs Rameau , Jaskanwal Deep Singh Sara , Stephanie W. Watts , Daria Hemmerling , Jiri Mekyska , Marisha L. Speights , the Bridge2AI Voice Consortium , the eVoiceNet COST Action (CA24128) , Jean-Christophe Bélisle-Pipon , Yael E. Bensoussan , Guy Fagherazzi medRxiv 2025.10.23.25338518; doi: https://doi.org/10.1101/2025.10.23.25338518 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Otolaryngology Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (300) Cardiovascular Medicine (4435) Dentistry and Oral Medicine (444) Dermatology (382) Emergency Medicine (608) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1509) Epidemiology (15228) Forensic Medicine (30) Gastroenterology (1124) Genetic and Genomic Medicine (6597) Geriatric Medicine (668) Health Economics (997) Health Informatics (4534) Health Policy (1368) Health Systems and Quality Improvement (1613) Hematology (540) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15916) Intensive Care and Critical Care Medicine (1103) Medical Education (623) Medical Ethics (146) Nephrology (667) Neurology (6599) Nursing (346) Nutrition (998) Obstetrics and Gynecology (1144) Occupational and Environmental Health (957) Oncology (3332) Ophthalmology (974) Orthopedics (369) Otolaryngology (420) Pain Medicine (436) Palliative Medicine (130) Pathology (663) Pediatrics (1693) Pharmacology and Therapeutics (691) Primary Care Research (711) Psychiatry and Clinical Psychology (5447) Public and Global Health (9230) Radiology and Imaging (2198) Rehabilitation Medicine and Physical Therapy (1370) Respiratory Medicine (1196) Rheumatology (593) Sexual and Reproductive Health (712) Sports Medicine (530) Surgery (712) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a00479461839dfa9',t:'MTc3OTU0MzY0MA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();